Jaiking001 commited on
Commit
0ea5e9a
·
verified ·
1 Parent(s): 2e19522

udated Model File

Browse files
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attn_logit_softcapping": null,
8
+ "bos_token_id": 2,
9
+ "cache_implementation": "hybrid",
10
+ "eos_token_id": [
11
+ 1,
12
+ 106
13
+ ],
14
+ "final_logit_softcapping": null,
15
+ "head_dim": 256,
16
+ "hidden_activation": "gelu_pytorch_tanh",
17
+ "hidden_size": 1152,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 6912,
20
+ "layer_types": [
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "sliding_attention",
26
+ "full_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "full_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "full_attention",
45
+ "sliding_attention",
46
+ "sliding_attention"
47
+ ],
48
+ "max_position_embeddings": 32768,
49
+ "model_type": "gemma3_text",
50
+ "num_attention_heads": 4,
51
+ "num_hidden_layers": 26,
52
+ "num_key_value_heads": 1,
53
+ "pad_token_id": 0,
54
+ "query_pre_attn_scalar": 256,
55
+ "rms_norm_eps": 1e-06,
56
+ "rope_local_base_freq": 10000,
57
+ "rope_scaling": null,
58
+ "rope_theta": 1000000,
59
+ "sliding_window": 512,
60
+ "sliding_window_pattern": 6,
61
+ "torch_dtype": "float32",
62
+ "transformers_version": "4.53.1",
63
+ "use_cache": true,
64
+ "vocab_size": 262144
65
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.53.1"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78bdf6c6237c82ba138aa16cf033211035840079628fb9121b7e4479d550fa3a
3
+ size 3999582960
special_tokens_map.json CHANGED
@@ -16,7 +16,13 @@
16
  "single_word": false
17
  },
18
  "image_token": "<image_soft_token>",
19
- "pad_token": "<eos>",
 
 
 
 
 
 
20
  "unk_token": {
21
  "content": "<unk>",
22
  "lstrip": false,
 
16
  "single_word": false
17
  },
18
  "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
  "unk_token": {
27
  "content": "<unk>",
28
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -51335,7 +51335,7 @@
51335
  },
51336
  "image_token": "<image_soft_token>",
51337
  "model_max_length": 1000000000000000019884624838656,
51338
- "pad_token": "<eos>",
51339
  "processor_class": "Gemma3Processor",
51340
  "sp_model_kwargs": null,
51341
  "spaces_between_special_tokens": false,
 
51335
  },
51336
  "image_token": "<image_soft_token>",
51337
  "model_max_length": 1000000000000000019884624838656,
51338
+ "pad_token": "<pad>",
51339
  "processor_class": "Gemma3Processor",
51340
  "sp_model_kwargs": null,
51341
  "spaces_between_special_tokens": false,